Schemas prod - Schema Manager

Schema Name: sfdl_prod_firehose.services_genesis_entity_pageview

created: 2018-08-24 13:47:50
disabled: False
format: raw
id: 519
is_partitioned: True
is_schema_datatyped: False

name:

{
    "database": "sfdl_prod_firehose",
    "table": "services_genesis_entity_pageview"
}

type: firehose

Schema Versions: 1

Version 41095

created: 2018-08-24 13:47:50

ddl:

[
    "CREATE DATABASE IF NOT EXISTS `sfdl_prod_firehose`",
    "DROP TABLE IF EXISTS `sfdl_prod_firehose.services_genesis_entity_pageview`",
    "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_firehose.services_genesis_entity_pageview`\n(\n `page_type_id`  string , `visit_id`  string , `confirmation_code`  string , `search_weight_id`  string , `first_page`  string , `unit_id`  string , `isoTimestamp`  string , `page_view_date`  string , `search_id`  string , `object_name`  string , `page_view_time`  string , `facility_id`  string , `request_uri`  string , `timestamp`  string , `site_content_id`  string , `search_weight_test_id`  string , `_origin`  string , `page_view_year_month`  string , `page_type`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView'\n",
    "MSCK REPAIR TABLE sfdl_prod_firehose.services_genesis_entity_pageview"
]

hive_path: s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView
id: 41095
processed: 1

raw_data:

{
    "_origin": "2018-08-24T18:47:08Z|separated_dt/Genesis_Entity_PageView/dt=2018-08-24/Genesis_Entity_PageView-2-2018-08-24-18-46-43-a6fa47f9-c4bf-4691-8fcb-12861322fec4.gz|firehose-prod",
    "confirmation_code": null,
    "facility_id": null,
    "first_page": 0,
    "isoTimestamp": "2018-08-24T13:46:41-05:00",
    "object_name": "Genesis_Entity_PageView",
    "page_type": "SITE_CONTENT",
    "page_type_id": null,
    "page_view_date": null,
    "page_view_time": "1969-12-31 18:00:00",
    "page_view_year_month": null,
    "request_uri": "https://www.sparefoot.com/Toms-River-NJ-self-storage.html",
    "search_id": "f22d5b80525459e7c1.73750876",
    "search_weight_id": "-1",
    "search_weight_test_id": null,
    "site_content_id": "99116",
    "timestamp": "20180824 13:46:41.3827",
    "unit_id": null,
    "visit_id": "807613f5b100693a81d440823a4899ad"
}

schema_attributes:

{
    "_origin": "string",
    "confirmation_code": "string",
    "facility_id": "string",
    "first_page": "string",
    "isoTimestamp": "string",
    "object_name": "string",
    "page_type": "string",
    "page_type_id": "string",
    "page_view_date": "string",
    "page_view_time": "string",
    "page_view_year_month": "string",
    "request_uri": "string",
    "search_id": "string",
    "search_weight_id": "string",
    "search_weight_test_id": "string",
    "site_content_id": "string",
    "timestamp": "string",
    "unit_id": "string",
    "visit_id": "string"
}

schema_name_id: 519
schema_scan_id: 16242916
updated: 2018-08-24 13:48:10

Schema Scans: 1

Last at 2018-08-24 13:47:50

Scan 16242916

duration: 0:00:13.741997

exit_message:

{
    "ddl_changed": true,
    "ingested_partitions": 1,
    "partitions_applied": false,
    "success": true
}

id: 16242916

payload:

{
    "datatype_dict": null,
    "file_format": "json",
    "is_schema_datatyped": false,
    "partition": {
        "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2018-08-24/",
        "name": "dt",
        "type": "string",
        "value": "2018-08-24"
    },
    "s3": {
        "bucket": "sfdl-firehose-services-prod",
        "hive_path": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView",
        "key": "separated_dt/Genesis_Entity_PageView/dt=2018-08-24/Genesis_Entity_PageView-2-2018-08-24-18-46-43-a6fa47f9-c4bf-4691-8fcb-12861322fec4.gz"
    },
    "schema": {
        "name": "sfdl_prod_firehose.services_Genesis_Entity_PageView",
        "type": "firehose"
    }
}

running: False
schema_name_id: 519
start_time: 2018-08-24 13:47:50
success: True
trace_id: 3290983200630913546

Partitions:

count: 3

ddl:

[
    "ALTER TABLE\n    `sfdl_prod_firehose.services_genesis_entity_pageview`\nADD\n\n\n PARTITION (dt='2020-08-16') location 's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-16/'\n PARTITION (dt='2020-08-17') location 's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-17/'\n PARTITION (dt='2020-08-18') location 's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-18/'\n;"
]

name: dt

state:

[
    {
        "info": {
            "id": 509342,
            "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-16/",
            "name": "dt",
            "value": "2020-08-16"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-08-15 19:01:31",
                "last_data": "2020-08-16 18:59:58"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 509516,
            "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-17/",
            "name": "dt",
            "value": "2020-08-17"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-08-16 19:01:24",
                "last_data": "2020-08-17 19:00:38"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    },
    {
        "info": {
            "id": 509694,
            "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-18/",
            "name": "dt",
            "value": "2020-08-18"
        },
        "state": {
            "arrival": {
                "athena_discovery": true,
                "first_data": "2020-08-17 19:01:39",
                "last_data": "2020-08-18 10:33:10"
            },
            "parquet": {
                "first_performed": null,
                "in_progress": null,
                "job_id": null,
                "last_performed": null,
                "queued": false
            }
        }
    }
]

type: string

Schema:

attributes:

{
    "_origin": "string",
    "confirmation_code": "string",
    "facility_id": "string",
    "first_page": "string",
    "isoTimestamp": "string",
    "object_name": "string",
    "page_type": "string",
    "page_type_id": "string",
    "page_view_date": "string",
    "page_view_time": "string",
    "page_view_year_month": "string",
    "request_uri": "string",
    "search_id": "string",
    "search_weight_id": "string",
    "search_weight_test_id": "string",
    "site_content_id": "string",
    "timestamp": "string",
    "unit_id": "string",
    "visit_id": "string"
}

created: 2018-08-24 13:47:50

ddl:

{
    "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_prod_firehose`",
    "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_firehose.services_genesis_entity_pageview`\n(\n `page_type_id`  string , `visit_id`  string , `confirmation_code`  string , `search_weight_id`  string , `first_page`  string , `unit_id`  string , `isoTimestamp`  string , `page_view_date`  string , `search_id`  string , `object_name`  string , `page_view_time`  string , `facility_id`  string , `request_uri`  string , `timestamp`  string , `site_content_id`  string , `search_weight_test_id`  string , `_origin`  string , `page_view_year_month`  string , `page_type`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView'\n",
    "drop_table": "DROP TABLE IF EXISTS `sfdl_prod_firehose.services_genesis_entity_pageview`",
    "repair_table": "MSCK REPAIR TABLE sfdl_prod_firehose.services_genesis_entity_pageview"
}

Server:

hostname: schemamanager-5475496c57-7dpqb
name: schema_manager
process_start: 2026-01-09 11:27:47
sf_env: prod
version: 2112174301

Raw:

{
    "name": {
        "created": "2018-08-24 13:47:50",
        "disabled": false,
        "format": "raw",
        "id": 519,
        "is_partitioned": true,
        "is_schema_datatyped": false,
        "name": {
            "database": "sfdl_prod_firehose",
            "table": "services_genesis_entity_pageview"
        },
        "type": "firehose"
    },
    "partition": {
        "count": 3,
        "ddl": [
            "ALTER TABLE\n    `sfdl_prod_firehose.services_genesis_entity_pageview`\nADD\n\n\n PARTITION (dt='2020-08-16') location 's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-16/'\n PARTITION (dt='2020-08-17') location 's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-17/'\n PARTITION (dt='2020-08-18') location 's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-18/'\n;"
        ],
        "name": "dt",
        "state": [
            {
                "info": {
                    "id": 509342,
                    "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-16/",
                    "name": "dt",
                    "value": "2020-08-16"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-08-15 19:01:31",
                        "last_data": "2020-08-16 18:59:58"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 509516,
                    "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-17/",
                    "name": "dt",
                    "value": "2020-08-17"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-08-16 19:01:24",
                        "last_data": "2020-08-17 19:00:38"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            },
            {
                "info": {
                    "id": 509694,
                    "location": "s3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView/dt=2020-08-18/",
                    "name": "dt",
                    "value": "2020-08-18"
                },
                "state": {
                    "arrival": {
                        "athena_discovery": true,
                        "first_data": "2020-08-17 19:01:39",
                        "last_data": "2020-08-18 10:33:10"
                    },
                    "parquet": {
                        "first_performed": null,
                        "in_progress": null,
                        "job_id": null,
                        "last_performed": null,
                        "queued": false
                    }
                }
            }
        ],
        "type": "string"
    },
    "schema": {
        "attributes": {
            "_origin": "string",
            "confirmation_code": "string",
            "facility_id": "string",
            "first_page": "string",
            "isoTimestamp": "string",
            "object_name": "string",
            "page_type": "string",
            "page_type_id": "string",
            "page_view_date": "string",
            "page_view_time": "string",
            "page_view_year_month": "string",
            "request_uri": "string",
            "search_id": "string",
            "search_weight_id": "string",
            "search_weight_test_id": "string",
            "site_content_id": "string",
            "timestamp": "string",
            "unit_id": "string",
            "visit_id": "string"
        },
        "created": "2018-08-24 13:47:50",
        "ddl": {
            "create_database": "CREATE DATABASE IF NOT EXISTS `sfdl_prod_firehose`",
            "create_table": "CREATE EXTERNAL TABLE IF NOT EXISTS\n`sfdl_prod_firehose.services_genesis_entity_pageview`\n(\n `page_type_id`  string , `visit_id`  string , `confirmation_code`  string , `search_weight_id`  string , `first_page`  string , `unit_id`  string , `isoTimestamp`  string , `page_view_date`  string , `search_id`  string , `object_name`  string , `page_view_time`  string , `facility_id`  string , `request_uri`  string , `timestamp`  string , `site_content_id`  string , `search_weight_test_id`  string , `_origin`  string , `page_view_year_month`  string , `page_type`  string \n)\nPARTITIONED BY (dt string)\nROW FORMAT SERDE\n'org.openx.data.jsonserde.JsonSerDe'\n \nSTORED AS INPUTFORMAT\n  'org.apache.hadoop.mapred.TextInputFormat'\nOUTPUTFORMAT\n  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'\nLOCATION\n  's3://sfdl-firehose-services-prod/separated_dt/Genesis_Entity_PageView'\n",
            "drop_table": "DROP TABLE IF EXISTS `sfdl_prod_firehose.services_genesis_entity_pageview`",
            "repair_table": "MSCK REPAIR TABLE sfdl_prod_firehose.services_genesis_entity_pageview"
        }
    },
    "server": {
        "hostname": "schemamanager-5475496c57-7dpqb",
        "name": "schema_manager",
        "process_start": "2026-01-09 11:27:47",
        "sf_env": "prod",
        "version": "2112174301"
    }
}

Schema Info